INDEX

Explanations

turns out

The neuron fires on copular/result verbs that introduce a finding or revelation—e.g. forms of “be,” “turn out,” “mean” (and their equivalents in other languages).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

</>

-1.84

}_{

-1.76

alties

-1.65

astify

-1.65

!"

-1.65

-1.63

ER

-1.62

StoryboardSegue

-1.57

isait

-1.56

('

-1.55

POSITIVE LOGITS

 decisivo

1.53

lève

1.53

 previsto

1.52

peated

1.46

cided

1.45

 دارند

1.43

 ventes

1.43



1.42

 związane

1.41

 displays

1.40

Activations Density 0.003%